Suzhou Electric Appliance Research Institute
期刊號: CN32-1800/TM| ISSN1007-3175

SUBSCRIPTION MANAGEMENT

發(fā)行征訂

首頁 >> 發(fā)行征訂 >> 征訂方式

基于注意力機制的ABG-GCA模型中長期風(fēng)電功率預(yù)測

來源:電工電氣發(fā)布時間:2025-03-03 15:03瀏覽次數(shù):5

基于注意力機制的ABG-GCA模型中長期風(fēng)電功率預(yù)測

蒲海濤1,2,代英健1
(1 山東科技大學(xué) 電氣與自動化工程學(xué)院,山東 青島 266590;
2 山東科技大學(xué)濟南校區(qū) 電氣信息系,山東 濟南 250031)
 
    摘 要:風(fēng)電功率預(yù)測對電力系統(tǒng)的穩(wěn)定性和經(jīng)濟性具有重要意義。針對已有模型預(yù)測時間較長和預(yù)測精度存在較大誤差的問題,提出了一種新型的 ABG-GCA 模型,該模型通過 Autoformer 的自相關(guān)機制與基于全局注意力機制的雙向門控循環(huán)單元將處理好的數(shù)據(jù)進行并行預(yù)測,對各分量的預(yù)測值利用交叉注意力機制來進行權(quán)重分配形成高效準(zhǔn)確功率的預(yù)測結(jié)果。實驗結(jié)果表明,該模型在預(yù)測精度和時間效率方面優(yōu)于傳統(tǒng)模型,能夠有效捕捉風(fēng)電功率的變化趨勢,對于不同季節(jié)的預(yù)測自適應(yīng)性極強且預(yù)測精度高。
    關(guān)鍵詞: 風(fēng)電功率預(yù)測;二次分解技術(shù);ABG-GCA 模型;中長期預(yù)測;自相關(guān)機制;全局注意力機制;交叉注意力機制;預(yù)測精度
    中圖分類號:TM614     文獻標(biāo)識碼:A     文章編號:1007-3175(2025)02-0010-09
 
Medium and Long Term Wind Power Prediction by ABG-GCA
Model Based on Attention Mechanism
 
PU Hai-tao1, 2, DAI Ying-jian1
(1 College of Electrical Engineering and Automation, Shandong University of Science and Technology, Qingdao 266590, China;
2 Electrical Information Department, Shandong University of Science and Technology-Jinan Campus, Jinan 250031, China)
 
    Abstract: The wind power prediction is of great significance to the stability and economy of power system. In this paper, a new ABGGCA model is proposed to solve the problem that the existing model has a long prediction time and a large error in prediction accuracy. The model uses the autocorrelation mechanism of Autoformer and the bidirectional gated recurrent unit based on the global attention mechanism to predict the processed data in parallel. The cross-attention mechanism is used to assign weights to the predicted values of each component to form an efficient and accurate power prediction result. The experimental results show that the model is superior to the traditional model,in terms of prediction accuracy and time efficiency which can effectively capture the change trend of wind power and prediction for different seasons has strong adaptability and high precision.
    Key words: wind power prediction; secondary decomposition technique; ABG-GCA model; medium and long term prediction; autocorrelation mechanism; global attention mechanism; cross-attention mechanism; prediction accuracy
 
參考文獻
[1] 汪欣. 基于神經(jīng)網(wǎng)絡(luò)的風(fēng)電功率優(yōu)化預(yù)測方法[D]. 上海:上海交通大學(xué),2020.
[2] ZHU Changsheng, ZHU Lina.Wind Speed Short-Term Prediction Based on Empirical Wavelet Transform, Recurrent Neural Network and Error Correction[J].Journal of Shanghai Jiaotong University(Science),2024,29(2) :297-308.
[3] CHEN Gonggui, LI Lijun, ZHANG Zhizhong, et al.Short-term wind speed forecasting with principle-subordinate predictor based on Conv-LSTM and improved BPNN[J].IEEE Access,2020,8 :67955-67973.
[4] 程杰,陳鼎,李春,等. 基于 GWO-CNN-BiLSTM 的超短期風(fēng)電預(yù)測[J] . 科學(xué)技術(shù)與工程,2023,23(35) :15091-15099.
[5] 符楊,任子旭,魏書榮,等. 基于改進 LSTM-TCN 模型的海上風(fēng)電超短期功率預(yù)測[J] . 中國電機工程學(xué)報,2022,42(12) :4292-4302.
[6] 郎偉明,麻向津,周博文,等.基于 LSTM 和非參數(shù)核密度估計的風(fēng)電功率概率區(qū)間預(yù)測[J].智慧電力,2020,48(2) :31-37.
[7] WANG W, FENG B, HUANG G, et al.Conformal asymmetric multi-quantile generative transformer for day-ahead wind power interval prediction[J].Applied Energy,2023,333 :120634.
[8] BENTSEN L D, WARAKAGODA N D, STENBRO R, et al. pSatiotemporal wind speed forecasting using graph networks and novel transformer architectures[J].Applied Energy,2023,333 :120565.
[9] WANG Lei, HE Yigang, LI Lie, et al.A novel approach to ultra-short-term multi-step wind power predictions based on encoder-decoder architecture in natural language processing[J].Journal of Cleaner Production,2022,354 :131723.
[10] 駱釗,吳諭侯,朱家祥,等. 基于多尺度時間序列塊自編碼 Transformer 神經(jīng)網(wǎng)絡(luò)模型的風(fēng)電超短期功率預(yù)測[J]. 電網(wǎng)技術(shù),2023,47(9) :3527-3536.
[11] 林錚,劉可真,沈賦,等. 考慮海上風(fēng)電多機組時空特性的超短期功率預(yù)測模型[J] . 電力系統(tǒng)自動化,2022,46(23) :59-66.
[12] WU Haixu, XU Jiehui, WANG Jianmin, et al.Autoformer: Decomposition transformers with autocorrelation for long-term series forecasting[J].Advances in Neural Information Processing Systems,2021,34 :22419-22430.
[13] 王渝紅,史云翔,周旭,等. 基于時間模式注意力機制的 BiLSTM 多風(fēng)電機組超短期功率預(yù)測[J]. 高電壓技術(shù),2022,48(5) :1884-1892.
[14] 宋柯. 基于多時間尺度及注意力機制的風(fēng)電功率預(yù)測技術(shù)研究[D]. 重慶:重慶理工大學(xué),2023.
[15] 李靜茹,姚方. 引入注意力機制的 CNN 和 LSTM 復(fù)合風(fēng)電預(yù)測模型[J]. 電氣自動化,2022,44(6) :4-6.
[16] 王家樂,張耀,林帆,等. 基于自注意力特征提取的光伏功率組合概率預(yù)測[J] . 太陽能學(xué)報,2024,45(12) :123-131.
[17] CAI J , ZHANG K , JIANG H . Power Quality Disturbance Classification Based on Parallel Fusion of CNN and GRU [J] . Energies,2023,16(10) :4029.
[18] 喬石,王磊,張鵬超,等. 基于時間模式注意力機制的 GRU 短期負荷預(yù)測[J] . 電力系統(tǒng)及其自動化學(xué)報,2023,35(10) :49-58.
[19] 龍鋮,余成波,何鋮,等. 基于雙重注意力機制 CNN-BiLSTM 與 LightGBM 誤差修正的超短期風(fēng)電功率預(yù)測[J].電氣工程學(xué)報,2024,19(2) :138-145.
[20] LUONG M T, PHAM H, MANNING C D.Effective approaches to attention-based neural machine translation[J].ArXiv Preprint ArXiv,2015,1508 :04025.